Engineers Study Self-Assessing Robots
PITTSBURGH—In the popular children’s book, “The Little Engine That Could,” the main character chants “I think I can, I think I can.” Engineers at Carnegie Mellon University’s Robotics Institute are trying to use a similar approach to give robots the ability of self-assessment.
The five-year research project is being funded by the Office of Naval Research.
“Robots [today] are ill-equipped to predict how well they can perform a task, or to sense if a task is going well, or even to know whether they did a good job once a task is completed,” says Aaron Steinfeld, associate research professor at the Robotics Institute.
“People use a number of tactics to judge whether or how well they can do something, such as throwing a baseball, turning a valve or drilling a hole in a wall,” explains Steinfeld. “As robots become
increasingly autonomous, they will need this ability, as well.”
According to Steinfeld, this self-assessment could be as simple as a robot being able to detect whether a task was completed satisfactorily. It could also include prediction and evaluation of proficiency. Or, in some cases, it might include a robot providing an explanation to a human about its performance.
“You’d like the robot to be able to explain why it can or why it can’t do a task, such as a self-driving car telling its occupants why it can’t drop them off at their requested destination,” says Steinfeld. “Identifying a lack of knowledge, dexterity or strength could enable a robot to work more efficiently with human partners.”
Steinfeld and his colleagues are testing various self-assessment approaches using dexterous search tasks for robots, such as maneuvering limbs to investigate obscured items, manipulating objects to reveal contents and adversarial manipulation.
“Such search tasks can be readily scaled up to applications such as robots deployed for emergency repairs, micro-drone swarms sent to map buildings, and urban search and rescue,” Steinfeld points out.